Talkative Chatbot Builder

Modified on Tue, 30 Jul at 2:02 PM


What is this feature and why you should use it?


A chatbot is a clever software application that simulates human conversation, chatting with users through text or voice. Chatbots are super helpful because they're available 24/7, so you never have to wait for answers. They provide quick, consistent responses to common questions, making life easier. By handling routine inquiries, chatbots let human agents focus on more complex issues, boosting efficiency and enhancing the overall customer experience.


Who can use this feature?


Licence:
Role:
Teams LicenceAgent
Business LicenceSupervisor
Enterprise LicenceAccount Holder


What will you learn from this article? 



1. Creating a chatbot config [2 minutes]

Before adding content to our chatbot, we must create a “chatbot config” to route the conversations. Follow the steps below to get this setup:

Notes:
- Queue emails are used if the chatbot sends a form to an email address.
- A timeout is not needed but is recommended at 10 minutes. Chats will end after that amount of inactivity. This time limit no longer applies if a chatbot is transferred or queued.


There are 3 template suggestions: 
    1. Example chatbot (beginner-friendly): a standard prebuilt example you can edit. 
    2. Generative AI chatbot (beginner-friendly): a standard prebuilt example you can edit with our AI integration.         (Only available on Enterprise packages.) 
    3. Blank slate (advanced): start at the beginning and build the outcomes you require from scratch. 



Managing Chatbot Versions:

In the create a chatbot config menu, you can access historical chatbot versions, if you need to revert to a previous version, or duplicate a previous version for editing:




2. Chatbots: Basic Navigation Video [5 minutes]





3. Chatbots: Key Concepts & Glossary


General Layout Overview:

There are 3 main sections within the chatbot builder display:


1. Top banner = Preview, Save and Publish. 

  • Preview Chatbot: The chat widget will open on the right, and you can simulate your customers' journey. To use preview, you will need to create a widget config.
  • Save: You should regularly save changes as you edit your chatbot.
  • PublishYou should only publish after checking the chatbot flows. Once you publish, your changes will be live for all your users!


2. Left = Chatbot Flow Diagram: 

Within this section, you’ll build out the pathways of options and conversation routes. 

  • Nodes: These are the square cards displayed which can be edited and customised with different actions and exit approaches. The parent node is the beginning, and child nodes continuing below. Use the + icon to add more nodes to that level of the flow diagram. 


3. Right = Node options and customisation: 

When you select a node card, it will be highlighted in purple on the flow chart, and the setting will appear on the right side. Different node types will have different dropdown options for editing the contents, these are explained below.



Node Options & Customisation:

General:

Edit the titles of your nodes to quickly identify what section of the journey a customer is at. This does not appear to the customer. 


Actions:

This is what the chatbot will be doing at each node. There are 5 action options you can choose from: 


Send Message(s)A  text-based customisable message sent to the customer.
Send FileA file is sent to the customer within the chat. You can upload any file type, but the size limit is 10 MB.
Make a web request and write int. DataIntegrating with external systems. For example, you can track an order for a user after retrieving their tracking number from the chatbotClick here for more information.
Custom Message Suggestions
Custom message suggestions allow you to create a suggestion chip without a corresponding follow up node. Use this if you want multiple suggestions to take you to a single follow up node, or when you want the user to free type to get to a specific node
Write Interaction Data
If you want to take the user’s input (e.g., email address) and have it create interaction data, you can set it to Static Text (a fixed value), the Entire Previous Message, Email in the Previous Message (the system auto-detects email values), or custom regex in the previous message (useful for detecting things like order numbers or account numbers).




Exit Approaches: 

Exit approaches are how the system decides which node to go to next. There are multiple options:



Branch off based on user inputThis is the most popular exit approach; the user’s message selection defines which node follows.
Always go to next itemIt waits for the user to message and then goes to the next input.
Redirect to next node immediatelyDoes not wait for the user input.
Transfer to queueLinks to the queues created within the Talkative queues settings section. The transfers will occur regardless of queue presence. 
Route based on interaction data valueThis allows you to pull through information you require, such as account numbers. You can then continue the flow to actions if it matches specific information. 
Route based on interaction data existenceFor example, only transfer to the sales queue if you have first captured the user's email address.
Based on queue statusUseful if you want to vary the message flow depending on whether your queue is online (or not).
Redirect to nodeAllows you to redirect across the flow to a different section. 
Lookup previous message in AI KnowledgebaseUsing generative AI to respond to a customer's question, based on a pre-approved data set (e.g. your website). Find out more here.
Escalate to email (web only)This will generate a form for the customer to fill in. The form will be emailed, and the agent will pick it up.
Redirect to the start of the chatbot flowReturns the chatbot to the starting point.
End interactionThe interaction will close.


Transfer to queue: We recommend you check the queue status. If you need to build a queue while building a chatbot, click save at the top and exit.


Warning: changing the exit approach will delete all descendants of this node. If you need to change an exit approach but want to retain the chatbot nodes below, we'd recommend copying/pasting the nodes you want to preserve.



Training Phases:

When selecting "Branch off based on user input", the training phases option will be available. The chatbot matches the user's text input to ‘training phrases’ within the target node. The user's input can be from free-text input or custom suggestions.

You can have multiple training phrases - the more you have, the more effective your chatbot will be at matching user input with intents/nodes.




AI matching to Training Phrases:

The chatbot uses AI to improve the matching of customer text input to nodes. It normalises the customer message and the training phrases, which means capitalised words and words with extra punctuation are matched.

If an exact match isn't found after normalisation, AI checks if the intention of the customer message is close to any of the phrases.


If you do not want messages being sent to an external AI service for this, please disable the AI enhancement config (settings > chatbot create/edit form). 




Message Suggestions:

If you select the Exit Approach of "Branch off based on user input" and you enter in the node names, these will show up as message suggestions in the original node.

In the example below, 3 nodes have been created, and their titles (Sales, Support, Speak to the Team) are automatically added as suggestions in the welcome node:



You can add suggestions, which will create a new node below:



Using the standard message suggestions, you cannot delete suggestions. If you want to have custom suggestions, or only display certain suggestions to users, click "Add Action" and then click "Custom Message Suggestions".



Retry Settings / Fallback:

Fallbacks are defined as the node that is hit if the chatbot does not understand the user's input. The Fallback node is set at the top of the tree on your first node. 



Retry settings are found at the starting point. Here you can edit the message sent when the chatbot responds to an input that isn't understood. You can have multiple retry messages. 


Maximum retry attempts counts the number of consecutive retries, rather than aggregate. For example, if you had retries set to 3, and then entered your email address incorrectly 2 times, but then entered it successfully on the 3rd attempt, then got to another fallback, the retry counter would be re-set to 0.



Errors:

If your chatbot has any errors in the logic/set up, you will see a warning in the top right corner. 

Click on this to take you to the issue node:




4. Shortcuts

Talkative supports several keyboard shortcuts:


Ctrl Z - UndoCtrl Y - RedoCtrl C - CopyCtrl V - Paste
Ctrl M - Minimise nodesCtrl P - SearchCtrl S - SaveCtrl Shift S - Publish
Ctrl+ Enter - Preview from startCtrl+Shift+Enter - Preview from current nodeCtrl B - Exit previewCtrl H - Scroll current node into view
Ctrl + - Zoom inCtrl - -  Zoom outBackspace/delete - Delete current node


Helpful onscreen Icons:
    Search is useful if you want to find a specific message or node.
    Minimise can be useful to get a simplified view of your chatbot displaying only the node title.



5. Frequently Asked Questions (FAQs)


    Q: How many chatbots can I have?

    A: There are currently no limits. You can build multiple different chatbots to suit different use cases.

 

    Q: How do I delete one node without deleting everything underneath?

    A: The best way to do this is Copy everything underneath that you want to keep, delete the node you want to delete, then paste. 

 

    Q: I love the idea of using Generative AI within my chatbot however I don't think it's included in my plan.

    A: You can book a quick call with a Customer Success Manager here to discover if AI could be useful to you. 


    Q: How do I delete some suggestion chips?

    A: You will need to click "Add Action" and then click "Custom Message Suggestions".


Was this article helpful?

That’s Great!

Thank you for your feedback

Sorry! We couldn't be helpful

Thank you for your feedback

Let us know how can we improve this article!

Select at least one of the reasons
CAPTCHA verification is required.

Feedback sent

We appreciate your effort and will try to fix the article